Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | <k.gemenis@utwente.nl> |
| To | <statalist@hsphsun2.harvard.edu> |
| Subject | RE: st: RE: Plotting interactions |
| Date | Mon, 30 Sep 2013 12:01:04 +0000 |
This is indeed an assumption of these .do files for the marginal effects plots. For many applications (not only in political science), computing marginal effects by holding control variables constant makes sense. In many instances one wants to see the marginal effect of X on Y across the levels of modifying variable Z assuming a host of controls that are not the primary interest of the investigated hypothesis (age, gender and what not) constant. This is definitely a limitation because if one wants to vary the controls they would have to compute multiple plots. Yet the provided .do files provide a pragmatic and intuitive approach in plotting interactions. Best, Kostas -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of David Hoaglin Sent: maandag 30 september 2013 13:52 To: statalist@hsphsun2.harvard.edu Subject: Re: st: RE: Plotting interactions Kostas, Thank you for sharing that URL. I looked at Matt Golder's explanation of his Stata code for the plot of the marginal effect of X in a regression model. Unfortunately, the partial derivative that defines the marginal effect mistakenly assumes that the "control variables" can be held constant. That is not how multiple regression works. And whether those other variables can actually be held constant depends on the data. I would avoid Golder's approach, even though those papers are highly cited. David Hoaglin On Mon, Sep 30, 2013 at 7:21 AM, <k.gemenis@utwente.nl> wrote: > Amal, > > Matt Golder has a bunch of .do files that make plotting interactions > very easy: https://files.nyu.edu/mrg217/public/interaction.html > > It is also worth looking at the associated papers that are highly cited among political scientists working with interactions. > > Best, > Kostas * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/